Expectation and interest about e-CRM are rising for more efficient customer management in on-line including electronic commerce. The decision-making tree can be used usefully as the data mining technology for e-CRM. In this paper, the representative decision making techniques, CART, C4.5, CHAID analyzed the differences in personalization point of view with actuality customer data through an experiment. With these analysis data, it is proposed a new decision-making tree system that has big advantage in personalization techniques. Through new system, it can get following advantage. First, it can form superior model more qualitatively in personalization by adding individual's weight value. Second it can supply information personalized more to customer. Third, it can have high position about customer's loyalty than other site of similar types of business. Fourth, it can reduce expense that cost marketing and decision-making. Fifth, it becomes possible that know that customer through smooth communication with customer who use personalized service wants and make from goods or service's quality to more worth thing.

In this report, we provide the focus on suggesting a method of estimating & measurement of CBM(Customer Behavior Model). Through the use of internet, a new trend of business for e-CRM on B2C Web Site which is now known as EC has emerged. The Purpose of this study is to identify the relationship between the customers of a shopping mall and CBM characteristics. Result showed that there is a significant relationship between the some customers pattern of shopping mall and CBM, CVM(Customer Visit Model).